mlsanityData to 7 Oct 2026

On-Robot Learning With Equivariant Models

arXiv 2203.04923 ↗First posted 9 Mar 2022cs.ROcited by 38

Not on the map. Why?

Abstract (arXiv)

Recently, equivariant neural network models have been shown to improve sample efficiency for tasks in computer vision and reinforcement learning. This paper explores this idea in the context of on-robot policy learning in which a policy must be learned entirely on a physical robotic system without reference to a model, a simulator, or an offline dataset. We focus on applications of Equivariant SAC to robotic manipulation and explore a number of variations of the algorithm. Ultimately, we demonstrate the ability to learn several non-trivial manipulation tasks completely through on-robot experiences in less than an hour or two of wall clock time.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Mar 2022.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 6; 2024: 11; 2025: 15; 2026: 4.

38 papers.

Sort:

By area:

  1. 2024Deep Reinforcement Learning for Robotics: A Survey of Real-World Successescited by 153
  2. 2024Equivariant Diffusion Policycited by 61
  3. 2023Diffusion-EDFs: Bi-equivariant Denoising Generative Modeling on SE(3) for Visual Robotic Manipulationcited by 51
  4. 2024Does equivariance matter at scale?cited by 49
  5. 2023Geometric Algebra Transformercited by 46
  6. 2023EDGI: Equivariant Diffusion for Planning with Embodied Agentscited by 35
  7. 2022The Surprising Effectiveness of Equivariant Models in Domains with Latent Symmetrycited by 32
  8. 2024Fourier Transporter: Bi-Equivariant Robotic Manipulation in 3Dcited by 32
  9. 2022SEIL: Simulation-augmented Equivariant Imitation Learningcited by 22
  10. 2023A General Theory of Correct, Incorrect, and Extrinsic Equivariancecited by 18
  11. 2024Imagination Policy: Using Generative Point Cloud Models for Learning Manipulation Policiescited by 18
  12. 2024Equivariant Reinforcement Learning under Partial Observabilitycited by 17
26 more
  1. 2025Do You Need Proprioceptive States in Visuomotor Policies?cited by 16
  2. 2025Touch begins where vision ends: Generalizable policies for contact-rich manipulationcited by 13
  3. 2024RiEMann: Near Real-Time SE(3)-Equivariant Robot Manipulation without Point Cloud Segmentationcited by 12
  4. 2024Morphological Symmetries in Roboticscited by 9
  5. 2025SE(3)-Equivariant Robot Learning and Control: A Tutorial Surveycited by 8
  6. 2024Improved Canonicalization for Model Agnostic Equivariancecited by 7
  7. 2025SE(3)-Equivariant Diffusion Policy in Spherical Fourier Spacecited by 7
  8. 2024MATCH POLICY: A Simple Pipeline from Point Cloud Registration to Manipulation Policiescited by 6
  9. 2023SO(2)-Equivariant Downwash Models for Close Proximity Flightcited by 5
  10. 2024Equivariant Offline Reinforcement Learningcited by 5
  11. 2025A Practical Guide for Incorporating Symmetry in Diffusion Policycited by 4
  12. 20253D Equivariant Visuomotor Policy Learning via Spherical Projectioncited by 4
  13. 2025EfficientFlow: Efficient Equivariant Flow Policy Learning for Embodied AIcited by 4
  14. 2025Morphologically Symmetric Reinforcement Learning for Ambidextrous Bimanual Manipulationcited by 3
  15. 2025Partially Equivariant Reinforcement Learning in Symmetry-Breaking Environmentscited by 3
  16. 2023On-Robot Bayesian Reinforcement Learning for POMDPscited by 2
  17. 2025Coarse-to-Fine 3D Keyframe Transportercited by 2
  18. 2025Generalizable Hierarchical Skill Learning via Object-Centric Representationcited by 2
  19. 2025Learning Abstract World Models with a Group-Structured Latent Spacecited by 1
  20. 2025On Uncertainty Calibration for Equivariant Functionscited by 1
  21. 2025Permutation Equivariant Neural Networks for Symmetric Tensorscited by 0
  22. 2025Multi-Group Equivariant Augmentation for Reinforcement Learning in Robot Manipulationcited by 0
  23. 2026Group-Invariant Unsupervised Skill Discovery: Symmetry-aware Skill Representations for Generalizable Behaviorcited by 0
  24. 2026SWAP: Symmetric Equivariant World-Model for Agile Robot Parkourcited by 0
  25. 2026Pix2Act: Image-Space Manipulation Policies with Equivariant Augmentationcited by 0
  26. 2026SymmGrid: Super-Scaling On-Robot Learning with Parallelized Symmetries and Egocentric-Exocentric Visual Perceptioncited by 0